{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/loans-weakly-supervised-object-detection-with","title":"LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks","arxiv_id":"1811.05773","date":"2018-11-14","proceeding":null,"authors":["Christian Bartz","Haojin Yang","Joseph Bethge","Christoph Meinel"],"abstract":"Recently, deep neural networks have achieved remarkable performance on the\ntask of object detection and recognition. The reason for this success is mainly\ngrounded in the availability of large scale, fully annotated datasets, but the\ncreation of such a dataset is a complicated and costly task. In this paper, we\npropose a novel method for weakly supervised object detection that simplifies\nthe process of gathering data for training an object detector. We train an\nensemble of two models that work together in a student-teacher fashion. Our\nstudent (localizer) is a model that learns to localize an object, the teacher\n(assessor) assesses the quality of the localization and provides feedback to\nthe student. The student uses this feedback to learn how to localize objects\nand is thus entirely supervised by the teacher, as we are using no labels for\ntraining the localizer. In our experiments, we show that our model is very\nrobust to noise and reaches competitive performance compared to a\nstate-of-the-art fully supervised approach. We also show the simplicity of\ncreating a new dataset, based on a few videos (e.g. downloaded from YouTube)\nand artificially generated data.","url_abs":"http://arxiv.org/abs/1811.05773v2","url_pdf":"http://arxiv.org/pdf/1811.05773v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"loans-weakly-supervised-object-detection-with","repo_url":"https://github.com/Bartzi/loans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}